M2HGCL: Multi-Scale Meta-Path Integrated Heterogeneous Graph Contrastive Learning

TL;DR

This paper introduces M2HGCL, a novel contrastive learning model for heterogeneous graphs that integrates multi-scale meta-path information without transforming the graph into a homogeneous structure, leading to improved performance.

Contribution

The paper proposes a multi-scale meta-path integrated contrastive learning approach that jointly aggregates various neighbor information in heterogeneous graphs, avoiding information loss from graph transformation.

Findings

M2HGCL outperforms state-of-the-art models on three real-world datasets.

Jointly aggregating multi-scale meta-paths enhances discriminative feature learning.

The proposed positive sampling strategy effectively addresses hard negative sampling issues.

Abstract

Inspired by the successful application of contrastive learning on graphs, researchers attempt to impose graph contrastive learning approaches on heterogeneous information networks. Orthogonal to homogeneous graphs, the types of nodes and edges in heterogeneous graphs are diverse so that specialized graph contrastive learning methods are required. Most existing methods for heterogeneous graph contrastive learning are implemented by transforming heterogeneous graphs into homogeneous graphs, which may lead to ramifications that the valuable information carried by non-target nodes is undermined thereby exacerbating the performance of contrastive learning models. Additionally, current heterogeneous graph contrastive learning methods are mainly based on initial meta-paths given by the dataset, yet according to our deep-going exploration, we derive empirical conclusions: only initial meta-paths cannot contain sufficiently discriminative information; and various types of meta-paths can effectively promote the performance of heterogeneous graph contrastive learning methods. To this end, we propose a new multi-scale meta-path integrated heterogeneous graph contrastive learning (M2HGCL) model, which discards the conventional heterogeneity-homogeneity transformation and performs the graph contrastive learning in a joint manner. Specifically, we expand the meta-paths and jointly aggregate the direct neighbor information, the initial meta-path neighbor information and the expanded meta-path neighbor information to sufficiently capture discriminative information. A specific positive sampling strategy is further imposed to remedy the intrinsic deficiency of contrastive learning, i.e., the hard negative sample sampling issue. Through extensive experiments on three real-world datasets, we demonstrate that M2HGCL outperforms the current state-of-the-art baseline models.